Paper Info
Title
A Path-Stack Algorithm For Optimizing Dynamic Regimes In A Statistical Hidden Dynamic Model Of Speech
Abstract
In this paper we report our recent research whose goal is to improve the performance of a novel speech recognizer based on an underlying statistical hidden dynamic model of phonetic reduction in the production of conversational speech. We have developed a path-stack search algorithm which efficiently computes the likelihood of any observation utterance while optimizing the dynamic regimes in the speech model. The effectiveness of the algorithm is tested on the speech data in the Switchboard corpus, in which the optimized dynamic regimes computed from the algorithm are compared with those from exhaustive search. We also present speech recognition results on the Switchboard corpus that demonstrate improvements of the recognizer's performance compared with the use of the dynamic regimes heuristically set from the phone segmentation by a state-of-the-art hidden Markov model (HMM) system. (C) 2000 Academic Press.
Year
DOI
Venue
2000
10.1006/csla.1999.0136
COMPUTER SPEECH AND LANGUAGE
Keywords
Field
DocType
exhaustive search,hidden markov model,search algorithm,speech recognition
Heuristic,Search algorithm,Brute-force search,Computer science,Segmentation,Algorithm,Utterance,Speech recognition,Phone,Speech model,Hidden Markov model
Journal
Volume
Issue
ISSN
14
2
0885-2308
Citations 
PageRank 
References 
10
1.30
11
Authors
2
Name
Order
Citations
PageRank
Jeff Z. Ma113315.79
Deng, Li29691728.14